Ingrid Larsen

ingrid-l

4 4

AI & ML interests

LLM reasoning, chain-of-thought prompting, mathematical reasoning, tree-of-thought

Recent Activity

liked a model about 10 hours ago

Yuhan123/vicuna-13b-self_consistency_neg_exp_var_2

upvoted a paper about 10 hours ago

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

liked a dataset 1 day ago

open-llm-leaderboard-old/details_alexredna__Tukan-1.1B-Chat-reasoning-sft-COLA

View all activity

Organizations

None yet

liked a model about 10 hours ago

Yuhan123/vicuna-13b-self_consistency_neg_exp_var_2

Updated Mar 14, 2025 • 2

upvoted a paper about 10 hours ago

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

Paper • 2609.16204 • Published 7 days ago • 4

liked 3 datasets 1 day ago

open-llm-leaderboard-old/details_alexredna__Tukan-1.1B-Chat-reasoning-sft-COLA

Updated Jan 22, 2024 • 80 • 3

nlpllmeval/NLP-Course-LLM-Reasoning-Eval-May2025

Viewer • Updated May 3, 2025 • 918 • 85 • 9

latkes/self-consistency-correction-exp23-correlation-discrimination

Viewer • Updated Apr 13 • 236 • 4 • 2

upvoted 2 papers 1 day ago

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

Paper • 2609.05405 • Published 17 days ago • 44

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Paper • 2609.15972 • Published 7 days ago • 8

upvoted a paper 3 days ago

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

Paper • 2609.13680 • Published 9 days ago • 11